Skip to content
llm-speed

llama3.2 on M1 Pro (16-core GPU) + 16GB unified

M1 Pro (16-core GPU) + 16GB unifiedM1 Pro (16-core GPU) + 16GB unified
suite suite-v1
cli 0.0.5
signed8raoNQEcn3…
Embed badgesubmitted Aug 18, 2026

Workload results

WorkloadBackendModeldecode tok/sprefill tok/sTTFTp50p95
chat-shortollama@0.32.14llama3.2Q8_0103.1tok/s8.77tok/s14,247ms9.4ms10.5ms
chat-longollama@0.32.14llama3.2Q8_081.35tok/s1,246.5tok/s2,529ms11.5ms14.9ms
concurrent-decodeollama@0.32.14llama3.2Q8_097.26tok/s9.9ms12.5ms
agent-traceollama@0.32.14llama3.2Q8_093.14tok/s2,975.3tok/s516ms10.5ms12.9ms

Reproduce on your machine

Same workload, same model, signed at your rig. The exact command that produced this run:

$ pipx install llm-speed && llm-speed bench --model 'llama3.2' --workload 'chat-short'

Runs in about a minute. Your number lands on the leaderboard signed and linkable. How it's measured.

Embed this run

Drop the badge into a README, blog post, or signature. Each render is a backlink to the signed result.

llm-speed: 103 tok/s on M1 Pro (16-core GPU) (llama3.2)
[![llm-speed: 103 tok/s on M1 Pro (16-core GPU) (llama3.2)](https://llm-speed.com/badge/r_w-p7v--eync.svg)](https://llm-speed.com/r/r_w-p7v--eync)

Related benchmarks

Provenance

Run ID
r_w-p7v--eync
Fingerprint hash
43f99b877c2d9bba
Public key
8raoNQEcn33R/v+VSYxZsgizfls+6Rnx9z8JnDkiXEs=
Received
2026-08-18 23:17:20